mkbk
119 lines
2.3 KiB
Python
119 lines
2.3 KiB
Python
from __future__ import annotations
|
|
|
|
from collections.abc import Callable, Iterable, Sequence
|
|
from typing import Protocol
|
|
|
|
from .models import (
|
|
AudioFrame,
|
|
AudioSegment,
|
|
Message,
|
|
PlaybackResult,
|
|
ReplyDelta,
|
|
Transcript,
|
|
TransportHealth,
|
|
VadResult,
|
|
WakeEvent,
|
|
)
|
|
|
|
|
|
class AudioTransport(Protocol):
|
|
def start_input(
|
|
self, device_id: str | None = None, sample_rate: int = 16000, channels: int = 1
|
|
) -> None:
|
|
...
|
|
|
|
def read_frames(self, timeout_ms: int) -> list[AudioFrame]:
|
|
...
|
|
|
|
def play_pcm(self, segment: AudioSegment, interrupt: bool = False) -> PlaybackResult:
|
|
...
|
|
|
|
def play_pcm_chunks(
|
|
self,
|
|
segment: AudioSegment,
|
|
*,
|
|
chunk_ms: int,
|
|
after_chunk: Callable[[AudioSegment, int], bool] | None = None,
|
|
should_stop: Callable[[], bool] | None = None,
|
|
) -> PlaybackResult:
|
|
...
|
|
|
|
def flush_input(self) -> int:
|
|
...
|
|
|
|
def stop(self) -> None:
|
|
...
|
|
|
|
def health(self) -> TransportHealth:
|
|
...
|
|
|
|
|
|
class WakeWordProvider(Protocol):
|
|
def load(self) -> None:
|
|
...
|
|
|
|
def detect(self, frame: AudioFrame) -> WakeEvent | None:
|
|
...
|
|
|
|
def reset(self) -> None:
|
|
...
|
|
|
|
|
|
class AudioPreprocessor(Protocol):
|
|
def load(self) -> None:
|
|
...
|
|
|
|
def reset(self) -> None:
|
|
...
|
|
|
|
def process_frame(self, frame: AudioFrame) -> AudioFrame:
|
|
...
|
|
|
|
def flush(self) -> list[AudioFrame]:
|
|
...
|
|
|
|
|
|
class VadProvider(Protocol):
|
|
def load(self) -> None:
|
|
...
|
|
|
|
def analyze(self, frame: AudioFrame) -> VadResult:
|
|
...
|
|
|
|
def reset(self) -> None:
|
|
...
|
|
|
|
|
|
class SttProvider(Protocol):
|
|
def load(self) -> None:
|
|
...
|
|
|
|
def transcribe(self, segment: AudioSegment) -> Transcript:
|
|
...
|
|
|
|
|
|
class RealtimeTranscriptSession(Protocol):
|
|
def accept_frame(self, frame: AudioFrame) -> Transcript | None:
|
|
...
|
|
|
|
def finish(self) -> Transcript | None:
|
|
...
|
|
|
|
|
|
class RealtimeSttProvider(SttProvider, Protocol):
|
|
def start_stream(self) -> RealtimeTranscriptSession:
|
|
...
|
|
|
|
|
|
class LlmProvider(Protocol):
|
|
def stream_reply(self, messages: Sequence[Message]) -> Iterable[ReplyDelta]:
|
|
...
|
|
|
|
|
|
class TtsProvider(Protocol):
|
|
def load(self) -> None:
|
|
...
|
|
|
|
def synthesize(self, text: str) -> AudioSegment:
|
|
...
|